Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Joe

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Trap
    -0.07
     GRID
    -0.07
    丈
    -0.06
     дит
    -0.06
     injunction
    -0.06
     Warrior
    -0.06
    َك
    -0.06
     traff
    -0.06
     strong
    -0.06
     eater
    -0.06
    POSITIVE LOGITS
     successive
    0.06
     fotbal
    0.06
    sol
    0.06
    θηκαν
    0.06
    ніх
    0.06
     seb
    0.06
    aned
    0.06
     ",
↵
    0.06
     fallback
    0.06
    letcher
    0.06
    Act Density 0.000%

    No Known Activations